Remote Mandarin AI Evaluation Specialist

Sovrano AI; Barcelona; On-site; EUR 17,000 - 34,000; Part time

Job summary

Sovrano AI is seeking a remote, hourly evaluator to review Mandarin AI responses for accuracy, fluency, and cultural fit. You will assess and compare answers, then craft strong model responses to guide learning.

You'll flag errors, log biases, and explain fixes to improve future outputs, ensuring tone, terminology, and nuance align with a Chinese audience. Flexible, global collaboration.

Qualifications

• Native Mandarin with real Mainland China usage
• Comfortable reading/writing English (B2+) to follow prompts
• Sharp eye for tone, register, naturalness
• Reliable and clear in documenting decisions
• Curious about AI and guidelines

Responsibilities

• Evaluate and rank Mandarin responses for accuracy, fluency, and context fit
• Write clear model answers and prompts illustrating correct reasoning
• Flag errors, bias, and phrasing and explain fixes for learning
• Check terminology, tone, and cultural nuances for a Chinese audience

Skills

Native Mandarin

English (B2+)

Attention to detail

Judgment on tone

Education

Degree in translation/linguistics

Tools

CAT tools

QA workflows

Job description

Sovrano AI is seeking a remote, hourly evaluator to review Mandarin AI responses for accuracy, fluency, and cultural fit. You will assess and compare answers, then craft strong model responses to guide learning.

You'll flag errors, log biases, and explain fixes to improve future outputs, ensuring tone, terminology, and nuance align with a Chinese audience. Flexible, global collaboration.